中文
相关论文

相关论文: Probabilistic Weight Fixing: Large-scale training …

200 篇论文

While offering a principled framework for uncertainty quantification in deep learning, the employment of Bayesian Neural Networks (BNNs) is still constrained by their increased computational requirements and the convergence difficulties…

机器学习 · 计算机科学 2025-05-26 Moule Lin , Shuhao Guan , Weipeng Jing , Goetz Botterweck , Andrea Patane

Modern neural network architectures have achieved remarkable accuracies but remain highly dependent on their training data, often lacking interpretability in their learned mappings. While effective on large datasets, they tend to overfit on…

机器学习 · 计算机科学 2025-03-19 Pavia Bera , Sanjukta Bhanja

Quantized Neural Networks (QNNs), which use low bitwidth numbers for representing parameters and performing computations, have been proposed to reduce the computation complexity, storage size and memory usage. In QNNs, parameters and…

计算机视觉与模式识别 · 计算机科学 2017-06-23 Shuchang Zhou , Yuzhi Wang , He Wen , Qinyao He , Yuheng Zou

Modern iterations of deep learning models contain millions (billions) of unique parameters, each represented by a b-bit number. Popular attempts at compressing neural networks (such as pruning and quantisation) have shown that many of the…

机器学习 · 计算机科学 2022-10-26 Christopher Subia-Waud , Srinandan Dasmahapatra

Bayesian neural networks (BNNs) are making significant progress in many research areas where decision-making needs to be accompanied by uncertainty estimation. Being able to quantify uncertainty while making decisions is essential for…

机器学习 · 计算机科学 2021-06-07 Martin Ferianc , Partha Maji , Matthew Mattina , Miguel Rodrigues

We introduce a new, efficient, principled and backpropagation-compatible algorithm for learning a probability distribution on the weights of a neural network, called Bayes by Backprop. It regularises the weights by minimising a compression…

机器学习 · 统计学 2015-05-22 Charles Blundell , Julien Cornebise , Koray Kavukcuoglu , Daan Wierstra

Deep Neural Networks (DNNs) have achieved extraordinary performance in various application domains. To support diverse DNN models, efficient implementations of DNN inference on edge-computing platforms, e.g., ASICs, FPGAs, and embedded…

机器学习 · 计算机科学 2020-12-15 Sung-En Chang , Yanyu Li , Mengshu Sun , Runbin Shi , Hayden K. -H. So , Xuehai Qian , Yanzhi Wang , Xue Lin

Bayesian Neural Networks (BNNs) provide a tool to estimate the uncertainty of a neural network by considering a distribution over weights and sampling different models for each input. In this paper, we propose a method for uncertainty…

机器学习 · 计算机科学 2024-10-28 Illia Oleksiienko , Dat Thanh Tran , Alexandros Iosifidis

In low-latency or mobile applications, lower computation complexity, lower memory footprint and better energy efficiency are desired. Many prior works address this need by removing redundant parameters. Parameter quantization replaces…

机器学习 · 计算机科学 2021-11-16 Cheng-Chou Lan

Robust machine learning models with accurately calibrated uncertainties are crucial for safety-critical applications. Probabilistic machine learning and especially the Bayesian formalism provide a systematic framework to incorporate…

机器学习 · 计算机科学 2022-10-11 Sumegha Premchandar , Sandeep Madireddy , Sanket Jantre , Prasanna Balaprakash

Model compression has gained a lot of attention due to its ability to reduce hardware resource requirements significantly while maintaining accuracy of DNNs. Model compression is especially useful for memory-intensive recurrent neural…

机器学习 · 计算机科学 2018-05-30 Dongsoo Lee , Byeongwook Kim

With the development of deep neural networks, the size of network models becomes larger and larger. Model compression has become an urgent need for deploying these network models to mobile or embedded devices. Model quantization is a…

机器学习 · 计算机科学 2019-07-02 Wen-Pu Cai , Wu-Jun Li

Compared to point estimates calculated by standard neural networks, Bayesian neural networks (BNN) provide probability distributions over the output predictions and model parameters, i.e., the weights. Training the weight distribution of a…

机器学习 · 计算机科学 2022-12-01 Philipp Wagner , Xinyang Wu , Marco F. Huber

Optimizing deep neural networks (DNNs) often suffers from the ill-conditioned problem. We observe that the scaling-based weight space symmetry property in rectified nonlinear network will cause this negative effect. Therefore, we propose to…

机器学习 · 计算机科学 2017-10-09 Lei Huang , Xianglong Liu , Bo Lang , Bo Li

Despite the huge success of deep neural networks (NNs), finding good mechanisms for quantifying their prediction uncertainty is still an open problem. Bayesian neural networks are one of the most popular approaches to uncertainty…

机器学习 · 统计学 2020-01-01 Agustinus Kristiadi , Sina Däubener , Asja Fischer

As machine learning systems get widely adopted for high-stake decisions, quantifying uncertainty over predictions becomes crucial. While modern neural networks are making remarkable gains in terms of predictive accuracy, characterizing…

机器学习 · 计算机科学 2019-06-14 Melanie F. Pradier , Weiwei Pan , Jiayu Yao , Soumya Ghosh , Finale Doshi-velez

Bayesian neural networks (BNNs) augment deep networks with uncertainty quantification by Bayesian treatment of the network weights. However, such models face the challenge of Bayesian inference in a high-dimensional and usually…

机器学习 · 计算机科学 2021-03-30 Zhijie Deng , Yucen Luo , Jun Zhu , Bo Zhang

Binary Neural Networks (BNNs) are an extremely promising method to reduce deep neural networks' complexity and power consumption massively. Binarization techniques, however, suffer from ineligible performance degradation compared to their…

机器学习 · 计算机科学 2022-04-06 Tal Rozen , Moshe Kimhi , Brian Chmiel , Avi Mendelson , Chaim Baskin

The deployment of deep neural networks on resource-constrained devices necessitates effective model com- pression strategies that judiciously balance the reduction of model size with the preservation of performance. This study introduces a…

机器学习 · 计算机科学 2025-05-02 Mohammad Zbeeb , Mariam Salman , Mohammad Bazzi , Ammar Mohanna

This paper proposes a novel binarized weight network (BT) for a resource-efficient neural structure. The proposed model estimates a binary representation of weights by taking into account the approximation error with an additional term.…

计算机视觉与模式识别 · 计算机科学 2021-05-11 Savas Ozkan , Gozde Bozdagi Akar
‹ 上一页 1 2 3 10 下一页 ›